ABSTRACT
Multidimensional data analysis (MDA) methods mainly provide synthetical representations of objects (most of the time these objects are individuals, variables, or categories of categorical variables) corresponding to the rows and columns of a data table. In MDA, the most typical method for representing a set of objects is a cloud of points (each point is an object), evolving in a Euclidean space (that can be reduced to a plane representation). The term “Euclidean” here refers to the fact that the distances between points (respectively the angles for the quantitative variables) are interpreted in terms of similarities for the individuals or categories (respectively in terms of correlation for the quantitative variables). Principal component methods, such as principal component analysis (PCA), correspondence analysis (CA), and multiple correspondence analysis (MCA), all yield Euclidean representations.
